Call this when the source font directory layout does not match the desired batch grouping. It defaults to dryRun true and is source-non-destructive: it never moves or deletes source files, and when dryRun is false it only copies selected fonts into outputDir. Inspect sourceSafetyDecision, layoutD...
AI agents use organize_font_directory to create or update resources in Mcp Font Split — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Mcp Font Split environment.
The tool copies files into an output directory when dryRun is false, which is a Write operation (creating new file copies). It explicitly does not delete or move source files, ruling out Destructive. The blast radius is medium: it could overwrite existing files in outputDir or produce unexpected directory structures if misconfigured, but source files are safe.
From the tool's definition it only copies selected fonts into outputDir — never moves or deletes source files; defaults to dryRun true; described as source-non-destructive
Attacks that exploit this kind of access
Call this when the source font directory layout does not match the desired batch grouping. It defaults to dryRun true and is source-non-destructive: it never moves or deletes source files, and when dryRun is false it only copies selected fonts into outputDir. Inspect sourceSafetyDecision, layoutDecision.directoryHandling, stagingDirectoryDecision, safetySummary, configurationTrace, batchPolicySummary, directoryWorkflowSummary, directoryWorkflowSummary.workflowSteps[].suggestedArgsField, sourceLayoutMismatchSummary, sourceLayoutMismatchSummary.decisionChecklist, sourceLayoutMismatchSummary.copyOnlyStaging.safePreviewArgs, recommendedBatchPreviewArgs, recommendedNextActions, recommendedNextActions[].suggestedArgsField, and outputTreeInsideInputTree because writesSourceTree can be true when outputDir is inside or equal to inputDir. recommendedBatchPreviewArgs preserves the current maxFiles scan cap for copyable follow-up previews; after copy-only writes sourceLayoutMismatchSummary.copyOnlyStaging.safePreviewArgs, sourceLayoutMismatchSummary.decisionChecklist.items[].safePreviewArgs, and the related workflowSteps suggestedArgs preserve it too; scanner follow-up recommendedNextActions[].suggestedArgs.maxFiles preserves it as well. stagingDirectoryDecision explicitly marks outputDir as source-like staging, not split output. For flat/nested/mixed/output-inside-input routing, get_agent_guidance sections:[. It is categorised as a Write tool in the Mcp Font Split MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Mcp Font Split MCP server in PolicyLayer and add a rule for organize_font_directory: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Mcp Font Split. Nothing to install.
organize_font_directory is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the organize_font_directory rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for organize_font_directory. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
organize_font_directory is provided by the Mcp Font Split MCP server (wenzhimo/mcp-font-split). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →